SOCO Benchmark
Explore score history ↗SOCO is a benchmark for semantic object correspondence with keypoint annotations across 100 categories and over 1M pairs. The evaluation is implemented within OmniProbe, which includes correspondence tasks among others.
- Released
- 2026-05-29
- Institutions
- Max Planck Institute for Informatics · Helmholtz Center for Information Security · University of Freiburg
- Evaluates
- General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SOCO paper and code
No reported scores are on record for this benchmark yet.